We consider the problem of segmenting an image into foreground and background, with foreground containing solely objects of interest known a priori. We propose an integration mode...
This paper considers a recently proposed method for unsupervised learning and dimensionality reduction, locally linear embedding (LLE). LLE computes a compact representation of hi...
Graph cuts have proven useful for image segmentation and for volumetric reconstruction in multiple view stereo. However, solutions are biased: the cost function tends to favour ei...
Abstract. We propose an efficient way to account for spatial smoothness in foreground-background segmentation of video sequences. Most statistical background modeling techniques re...
We present an algorithm that extracts curves from a set of edgels within a specific class in a decreasing order of their ``length''. The algorithm inherits the perceptual...